INDEX

Explanations

the word "here"

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "here" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ORPG

-0.63

acci

-0.63

framework

-0.62

efe

-0.61

ONSORED

-0.59

emaker

-0.57

dp

-0.57

-0.56

successful

-0.55

POSITIVE LOGITS

abouts

1.08

tics

0.97

 goes

0.97

tical

0.93

upon

0.89

ya

0.88

 Comes

0.87

 comes

0.81

tic

0.75

 emerges

0.73

Activations Density 0.103%

the word "here"

the repeated use of the word "here" in various contexts

No Comments

No Known Activations